Add files using upload-large-folder tool

README.md

@@ -0,0 +1,207 @@
+---
+library_name: transformers
+inference: false
+extra_gated_description: >-
+  To learn more about how we process your personal data, please read our <a
+  href="https://poolside.ai/legal/privacy">Privacy Policy</a>.
+tags:
+- laguna-s-2.1
+- vllm
+- quantized
+- rfa
+- 4-bit
+license: openmdw-1.1
+pipeline_tag: text-generation
+base_model:
+- poolside/Laguna-S-2.1
+base_model_relation: quantized
+---
+
+> [!IMPORTANT]
+> ## Linear-RFA 4-bit quant of [poolside/Laguna-S-2.1](https://huggingface.co/poolside/Laguna-S-2.1)
+>
+> This is `tcclaviger/Laguna-S-2.1-RFA_L` — an RFA 4-bit quantization of Poolside's
+> **Laguna-S-2.1**. The `_L` (linear-only) build quantizes the MLP and expert linear
+> layers to 4-bit (IQ4_NL grid, group 16, Hadamard-16 rotation, asymmetric block-float
+> scales) while keeping **all attention, the router gate, and the lm_head in bf16**.
+> 71.2 GB total, 4.504 bits/weight. All credit for the model to Poolside; this repo only
+> changes the numerics. **The full original model card is preserved verbatim below.**
+>
+> **Runtime:** requires [`tcclaviger/vllm:latest`](https://hub.docker.com/r/tcclaviger/vllm) — an **RDNA 4 (gfx12xx)** vLLM image and the only build with the RFA kernels; no other vLLM build loads these weights. **Not validated on any other hardware at this time.**
+>
+> **DFlash speculative decoding works with this RFA checkpoint.** Pair it with the
+> [Laguna-S-2.1-DFlash](https://huggingface.co/poolside/Laguna-S-2.1-DFlash) draft model
+> exactly as documented in the vLLM section below — the RFA quant does not touch the
+> attention path, so the DFlash draft head runs unchanged.
+
+---
+
+<p align="center">
+  <img alt="poolside-banner" src="https://poolside.ai/assets/laguna/laguna-s-2-1-banner.svg" width="800px">
+</p>
+
+<p align="center">
+  <a href="https://openrouter.ai/poolside/laguna-s-2.1"><strong>Use on OpenRouter</strong></a> ·
+  <a href="https://vercel.com/ai-gateway/models/laguna-s-2.1"><strong>Use on Vercel AI Gateway</strong></a> ·
+  <a href="https://poolside.ai/blog/introducing-laguna-s-2-1"><strong>Release blog post</strong></a>
+</p>
+
+<br>
+
+# Laguna S 2.1
+
+Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated
+parameters per token, designed for agentic coding and long-horizon work. It sits
+between [Laguna XS 2.1](https://huggingface.co/poolside/Laguna-XS-2.1) (33B-A3B) and
+Laguna M.1 (225B-A23B) in the Laguna series and shares the family recipe: a
+token-choice router with softplus gating over 256 routed experts plus one shared
+expert, grouped-query attention, and interleaved full/sliding-window attention.
+
+## Highlights
+
+- **Mixed SWA and global attention layout**: 48 layers in a 1:3 global-to-SWA ratio
+  (12 global attention layers, 36 sliding-window layers, window 512), with softplus
+  attention gating and per-layer-type rotary scales
+- **1M context**: 1,048,576-token context window
+- **Native reasoning support**: interleaved thinking between tool calls, with
+  per-request control via `enable_thinking`
+- **Speculative decoding**: a trained
+  [DFlash draft model](https://huggingface.co/poolside/Laguna-S-2.1-DFlash) is available
+  for lower-latency serving
+- **Quantized variants**:
+  [FP8](https://huggingface.co/poolside/Laguna-S-2.1-FP8),
+  [NVFP4](https://huggingface.co/poolside/Laguna-S-2.1-NVFP4),
+  [INT4](https://huggingface.co/poolside/Laguna-S-2.1-INT4) and
+  [GGUF](https://huggingface.co/poolside/Laguna-S-2.1-GGUF)
+- **OpenMDW-1.1 license**: Use and modify the model and associated materials freely
+  for commercial and non-commercial purposes
+  ([learn more about OpenMDW](https://openmdw.ai/))
+
+## Model overview
+
+- Number of parameters: 118B total, ~8B activated per token
+- Layers: 48 (12 global attention, 36 sliding-window attention)
+- Experts: 256 routed (top-10) plus 1 shared expert
+- Attention: grouped-query, 8 KV heads, head dim 128; per-head softplus output gating
+- Sliding window: 512 tokens
+- Context window: 1,048,576 tokens
+- Vocabulary: 100,352 tokens (Laguna family tokenizer)
+- Modality: text-to-text
+- Reasoning: interleaved thinking with preserved thinking
+
+## Benchmark results
+
+<p align="center">
+  <img alt="benchmarks" src="https://poolside.ai/assets/laguna/laguna-s-2-1-chart.svg" width="800px">
+</p>
+
+| Model | Size | Terminal-Bench 2.1 | SWE-bench Multilingual | SWE-Bench Pro (Public Dataset) | DeepSWE | SWE Atlas (Codebase QnA) | Toolathlon Verified |
+|---|---|---|---|---|---|---|---|
+| **Laguna S 2.1** | 118B-A8B | **70.2%** | **78.5%** | **59.4%** | **40.4%** | **46.2%** | **49.7%** |
+| Tencent Hy3 | 295B-A21B | 71.7% | 75.8% | 57.9% | - | - | - |
+| Inkling | 975B-A41B | 63.8% | - | 54.3% | - | - | 45.5%* |
+| Nemotron 3 Ultra | 550B-A55B | 56.4% | 67.7% | - | - | - | 34.3%* |
+| DeepSeek-V4-Pro Max | 1.6T-A49B | 64.0%* | 76.2% | 55.4% | 9.0%* | 27.2%* | 55.9%* |
+| Kimi K3 | 2800B-A50B | 88.3% | - | - | 69% | - | - |
+| Qwen 3.7 Max | - | 74.5%* | 78.3% | 60.6% | - | - | - |
+| Muse Spark 1.1 | - | 80% | - | 61.5% | 53.3% | 42.2%* | 75.6% |
+| Claude Fable 5 | - | 88% | - | 80.3% | 70% | - | - |
+
+Benchmarks as of 21 July 2026. Laguna S 2.1 in **bold**; a dash (-) marks a benchmark a model was not evaluated on. Scores marked * are as reported by third parties: Terminal-Bench 2.1 and DeepSWE via Artificial Analysis, SWE Atlas via Scale AI's official leaderboard, and Toolathlon Verified via its official leaderboard. Full evaluation trajectories: [trajectories.poolside.ai](https://trajectories.poolside.ai).
+
+## Usage
+
+Laguna S 2.1 uses the same `laguna` architecture as Laguna XS 2.1, so the same
+engine integrations apply (vLLM, SGLang, Transformers, TRT-LLM, llama.cpp). At 118B
+parameters the BF16 checkpoint needs multiple GPUs (roughly 236GB of weights);
+quantized variants reduce this substantially.
+
+### vLLM
+
+```shell
+vllm serve \
+    --model poolside/Laguna-S-2.1 \
+    --tensor-parallel-size 4 \
+    --tool-call-parser poolside_v1 \
+    --reasoning-parser poolside_v1 \
+    --enable-auto-tool-choice \
+    --served-model-name laguna \
+    --default-chat-template-kwargs '{"enable_thinking": true}'
+```
+
+> [!NOTE]
+> **Optional: speculative decoding with DFlash.** Pair with the
+> [Laguna S 2.1 DFlash draft model](https://huggingface.co/poolside/Laguna-S-2.1-DFlash)
+> by adding
+> `--speculative-config '{"model":"poolside/Laguna-S-2.1-DFlash","num_speculative_tokens":7,"method":"dflash"}'`.
+
+### SGLang
+
+```shell
+python -m sglang.launch_server \
+  --model-path poolside/Laguna-S-2.1 \
+  --tp-size 4 \
+  --reasoning-parser poolside_v1 \
+  --tool-call-parser poolside_v1 \
+  --trust-remote-code
+```
+
+### TRT-LLM
+
+```shell
+trtllm-serve poolside/Laguna-S-2.1 --trust-remote-code \
+    --tool_parser poolside_v1 --reasoning_parser laguna
+```
+
+Note the flag names differ from vLLM's (`--tool_parser`, and the reasoning parser
+is `laguna`, not `poolside_v1`).
+
+### llama.cpp
+
+GGUF conversions are available at
+[poolside/Laguna-S-2.1-GGUF](https://huggingface.co/poolside/Laguna-S-2.1-GGUF).
+Serve with poolside's llama.cpp fork, branch
+[`laguna`](https://github.com/poolsideai/llama.cpp/tree/laguna), which carries
+full Laguna support including DFlash speculative decoding. (Base Laguna support
+is also in upstream review:
+[ggml-org/llama.cpp#25165](https://github.com/ggml-org/llama.cpp/pull/25165).)
+
+```shell
+git clone --branch laguna https://github.com/poolsideai/llama.cpp
+cd llama.cpp && cmake -B build && cmake --build build -j
+
+./build/bin/llama-server -m laguna-s-2.1-Q4_K_M.gguf --jinja --port 8000
+
+# with DFlash speculative decoding:
+./build/bin/llama-server -m laguna-s-2.1-Q4_K_M.gguf \
+  -md laguna-s-2.1-DFlash-BF16.gguf \
+  --spec-type draft-dflash --spec-draft-n-max 7 -fa on --jinja --port 8000
+```
+
+## Controlling reasoning
+
+Laguna S 2.1 has native reasoning support and works best with *preserved thinking*:
+keep `reasoning_content` from prior assistant messages in the message history.
+The model will generally reason before calling tools and between tool calls, and
+may stop reasoning in follow-up steps if prior thinking blocks are dropped.
+
+Thinking is controlled per request via the chat template:
+
+```python
+extra_body={"chat_template_kwargs": {"enable_thinking": False}}
+```
+
+or at the server level with
+`--default-chat-template-kwargs '{"enable_thinking": true}'`. For agentic coding
+use cases we recommend enabling thinking and preserving reasoning in the message
+history.
+
+## License
+
+This model is licensed under the [OpenMDW-1.1 License](https://huggingface.co/poolside/Laguna-S-2.1/blob/main/LICENSE.md).
+
+## Intended and Responsible Use
+
+Laguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the [OpenMDW-1.1 License](https://huggingface.co/poolside/Laguna-S-2.1/blob/main/LICENSE.md), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
+
+Please report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).

chat_template.jinja

@@ -0,0 +1,94 @@
+{#- Iteration on laguna_glm_thinking_v8/chat_template.jinja -#}
+{#- No formatting instructions -#}
+{{- "〈|EOS|〉" -}}
+{%- set enable_thinking = enable_thinking | default(true) -%}
+{%- set add_generation_prompt = add_generation_prompt | default(false) -%}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+
+{#- ───── header (system message) ───── -#}
+{#- A caller-supplied system message with empty content opts out of the default below, producing no <system> block — used to train without a system message. -#}
+{%- set system_message = "You are a helpful, conversationally-fluent assistant made by Poolside. You are here to be helpful to users through natural language conversations." -%}
+{%- if messages and messages[0].role == "system" -%}
+  {%- set system_message = messages[0].content -%}
+  {%- set messages = messages[1:] -%}
+{%- endif -%}
+
+{%- set has_sys = system_message and system_message.strip() -%}
+{%- if has_sys or tools or enable_thinking -%}
+  {{- "<system>" -}}
+
+  {%- if has_sys -%}
+    {{- system_message.rstrip() -}}
+    {%- if tools -%}{{- "\n\n" -}}{%- endif -%}
+  {%- endif -%}
+
+  {%- if tools -%}
+    {{- "### Tools\n\n" -}}
+    {{- "You may call functions to assist with the user query.\n" -}}
+    {{- "All available function signatures are listed below:\n" -}}
+    {{- "<available_tools>\n" -}}
+    {%- for tool in tools -%}
+      {{- (tool | tojson) ~ "\n" -}}
+    {%- endfor -%}
+    {{- "</available_tools>" -}}
+  {%- endif -%}
+
+  {{- "</system>\n" -}}
+{%- endif -%}
+
+{#- ───── main loop ───── -#}
+{%- for message in messages -%}
+  {%- set content = message.content if message.content is string else "" -%}
+  {%- if message.role == "user" -%}
+    {{- "<user>" + content + "</user>\n" -}}
+  {%- elif message.role == "assistant" -%}
+    {%- generation -%}
+      {{- "<assistant>" -}}
+      {#- Extract reasoning content from message.reasoning (vLLM field name) or message.reasoning_content -#}
+      {%- set reasoning_content = '' -%}
+      {%- if message.reasoning is string -%}
+        {%- set reasoning_content = message.reasoning -%}
+      {%- elif message.reasoning_content is string -%}
+        {%- set reasoning_content = message.reasoning_content -%}
+      {%- endif -%}
+      {#- Display reasoning content for all messages if enable_thinking -#}
+      {%- if enable_thinking or preserve_thinking -%}
+        {{- '<think>' + reasoning_content + '</think>' -}}
+      {%- else -%}
+        {{- '</think>' -}}
+      {%- endif -%}
+      {#- Display main content (trailing newline only when no tool_calls follow) -#}
+      {%- if content -%}
+        {{- content -}}
+      {%- endif -%}
+      {%- if message.tool_calls -%}
+        {%- for tool_call in message.tool_calls -%}
+          {%- set function_data = tool_call.function -%}
+          {{- '<tool_call>' + function_data.name -}}
+          {%- set _args = function_data.arguments -%}
+          {%- for k, v in _args.items() -%}
+            {{- "<arg_key>" ~ k ~ "</arg_key>" -}}
+            {{- "<arg_value>" -}}{{- v | tojson(ensure_ascii=False) if v is not string else v -}}{{- "</arg_value>" -}}
+          {%- endfor -%}
+          {{- "</tool_call>" -}}
+        {%- endfor -%}
+      {%- endif -%}
+      {{- "</assistant>\n" -}}
+    {%- endgeneration -%}
+  {%- elif message.role == "tool" -%}
+    {{- "<tool_response>" + content + "</tool_response>\n" -}}
+  {%- elif message.role == "system" -%}
+    {#- Render additional system messages (the first one, if any, is handled separately in the header and was sliced off above) -#}
+    {{- "<system>" + content + "</system>\n" -}}
+  {%- endif -%}
+{%- endfor -%}
+{#- ───── generation prompt ───── -#}
+{%- if add_generation_prompt -%}
+  {{- "<assistant>" -}}
+  {#- ───── Include reasoning mode directive ───── -#}
+  {%- if enable_thinking -%}
+    {{- '<think>' -}}
+  {%- else -%}
+    {{- '</think>' -}}
+  {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,312 @@
+{
+  "architectures": [
+    "LagunaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_laguna.LagunaConfig",
+    "AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM"
+  },
+  "model_type": "laguna",
+  "vocab_size": 100352,
+  "hidden_size": 3072,
+  "intermediate_size": 12288,
+  "num_hidden_layers": 48,
+  "num_attention_heads": 48,
+  "num_key_value_heads": 8,
+  "head_dim": 128,
+  "max_position_embeddings": 1048576,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "rms_norm_eps": 1e-06,
+  "num_experts": 256,
+  "num_experts_per_tok": 10,
+  "moe_intermediate_size": 1024,
+  "shared_expert_intermediate_size": 1024,
+  "norm_topk_prob": true,
+  "router_aux_loss_coef": 0.0,
+  "decoder_sparse_step": 1,
+  "mlp_only_layers": [
+    0
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": [
+    2,
+    24
+  ],
+  "pad_token_id": 9,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "torch_dtype": "bfloat16",
+  "gating": "per-head",
+  "sliding_window": 512,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 500000.0,
+      "rope_type": "yarn",
+      "factor": 128.0,
+      "original_max_position_embeddings": 8192,
+      "beta_slow": 1.0,
+      "beta_fast": 32.0,
+      "attention_factor": 1.4852030263919618,
+      "partial_rotary_factor": 0.5
+    },
+    "sliding_attention": {
+      "rope_type": "default",
+      "rope_theta": 10000.0,
+      "partial_rotary_factor": 1.0
+    }
+  },
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "moe_apply_router_weight_on_input": false,
+  "mlp_layer_types": [
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "gating_types": [
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head",
+    "per_head"
+  ],
+  "moe_routed_scaling_factor": 2.5,
+  "num_attention_heads_per_layer": [
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72,
+    48,
+    72,
+    72,
+    72
+  ],
+  "moe_router_logit_softcapping": 0.0,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "rfa-pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "num_bits": 4,
+          "type": "float",
+          "group_size": 16,
+          "grid": "iq4_nl",
+          "codebook": [
+            -127,
+            -104,
+            -83,
+            -65,
+            -49,
+            -35,
+            -22,
+            -10,
+            1,
+            13,
+            25,
+            38,
+            53,
+            69,
+            89,
+            113
+          ],
+          "scale_dtype": "torch.int8",
+          "scale_exp_dtype": "torch.int8",
+          "scale_encoding": "block_float_i8m_i8e",
+          "symmetric": false,
+          "rotation": "hadamard16"
+        }
+      }
+    },
+    "format": "rfa-pack-quantized",
+    "quant_method": "rfa",
+    "quantization_status": "compressed",
+    "version": "rfa-1.0",
+    "ignore": [
+      "re:.*\\.self_attn\\..*",
+      "re:.*\\.mlp\\.gate\\.weight$",
+      "re:^lm_head"
+    ]
+  }
+}

eval_metrics.txt

@@ -0,0 +1,27 @@
+=== Laguna-S-2.1-RFA ===
+arch: laguna
+codebook: [-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113]
+rotation: hadamard16
+
+[integrity] shards=13 missing=none
+[integrity] index total_size=71.16GB  on-disk safetensors sum=71.17GB
+[integrity] tensors: index=109249 headers=109249 OK
+
+[coverage] quantized expert-mods=0 linear-mods=36240 fp16-protected=0 copied=529
+[coverage] missing/bad: 0
+
+[bpw] quant-target params=114.10B  rfa bytes=64.25GB  -> 4.504 bits/weight
+[size] total=71.16GB = rfa 64.25GB + copied(bf16/other) 6.91GB
+
+[fidelity] dequant vs source (relFro / SQNR):
+   model.layers.0.mlp.down_proj  relFro=6.150%  SQNR=24.2 dB
+   model.layers.0.mlp.gate_proj  relFro=6.311%  SQNR=24.0 dB
+   model.layers.0.mlp.up_proj  relFro=6.304%  SQNR=24.0 dB
+   model.layers.24.mlp.experts.0.down_proj  relFro=6.328%  SQNR=24.0 dB
+   model.layers.24.mlp.experts.0.gate_proj  relFro=6.334%  SQNR=24.0 dB
+   model.layers.24.mlp.experts.0.up_proj  relFro=6.335%  SQNR=24.0 dB
+   model.layers.47.mlp.experts.0.down_proj  relFro=6.338%  SQNR=24.0 dB
+   model.layers.47.mlp.experts.0.gate_proj  relFro=6.340%  SQNR=24.0 dB
+   model.layers.47.mlp.experts.0.up_proj  relFro=6.336%  SQNR=24.0 dB
+
+DONE

generation_config.json

@@ -0,0 +1,24 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    24
+  ],
+  "pad_token_id": 9,
+  "temperature": 1.0,
+  "top_p": 1.0,
+  "min_p": 0.0,
+  "top_k": 20,
+  "tool_call_parser": "poolside_v1",
+  "reasoning_parser": "poolside_v1",
+  "default_chat_template_kwargs": {
+    "enable_thinking": true
+  },
+  "speculative_config": {
+    "method": "dflash",
+    "source": "huggingface",
+    "model": "poolside/Laguna-S-2.1-DFlash",
+    "num_speculative_tokens": 15
+  }
+}

model-00000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d288cc71cc76e4f0b187afb27e55fb844f2a2cdf583fc227f9856a9173afbd9
+size 5395952168

model-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04eba164f38c5c0362032e3c68894936e0f5d5fab27eaf69a873baee977aaf1a
+size 5679441824

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f513e4fc9168f2c996d73b9a24af34dcd15594d06885dee96c30a8cc6495773b
+size 5463493712

model-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f7b7fcd069a159b2ac06d0decf6bd5ffdf0d4cc329f1f6d9d92315b054c17c
+size 5463498336

model-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa012bcc06f5011019cfb525f4b386a546aefcfdcf333bc2d80601207c12c57
+size 5463502960

model-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768579b5e91415bd58368b5aa8ac473bba50bfd36f6eb19ca2d6fe1f2b99c929
+size 5463502960

model-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f69ec37d26ca2a23938f96f6651526b676d4365cbaa9680484245c25312349
+size 5463502960

model-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd526feafed49e8d23e481b8c3e3001fca5f38ff5a6a81a644f27d5afdd951d9
+size 5463502960

model-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3934c683bc4ca23b05e2853a1c928e2207a59a6459ef8aecbbcbbee976b088
+size 5463502960

model-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d58fc61a1ed6762d70a5d561336c3ac00a138beaa9affd4d669de220a6fc41
+size 5463502960

model-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d8bc5e29e307d4da3031314f5f6cca80696daf62822cccb665fd8a19a414ce
+size 5463502960

model-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41ef40dba5edf23d919c39b86be389c3e62e9668c37c6aa406d982c146d95ab
+size 5463502960

tokenizer_config.json

@@ -0,0 +1,576 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "〈|UNK|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "〈|CODE_START|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "〈|EOS|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "〈|CODE_END|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "〈|META_START|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "〈|META_END|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "〈|FIM_MIDDLE|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "〈|FIM_SUFFIX|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "〈|SEP|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "〈|PAD|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "〈|CLS|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "〈|FIM_START|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "〈|MASK|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "|◊|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "〈|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "〈|/",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "/|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "〈|SPECIAL_1|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "〈|SPECIAL_2|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "〈|SPECIAL_3|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "〈|SPECIAL_8|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "〈|SPECIAL_9|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "〈|SPECIAL_10|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "〈|SPECIAL_11|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "〈|SPECIAL_12|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "〈|SPECIAL_13|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "〈|SPECIAL_14|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "〈|SPECIAL_15|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "〈|SPECIAL_16|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "〈|SPECIAL_17|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "〈|SPECIAL_18|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "〈|SPECIAL_19|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "〈|SPECIAL_20|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "〈|SPECIAL_21|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "content": "〈|SPECIAL_22|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "〈|SPECIAL_23|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "content": "〈|SPECIAL_24|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44": {
+      "content": "〈|SPECIAL_25|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "〈|SPECIAL_26|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "〈|SPECIAL_27|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "47": {
+      "content": "〈|SPECIAL_28|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "48": {
+      "content": "〈|SPECIAL_29|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49": {
+      "content": "〈|SPECIAL_30|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50": {
+      "content": "〈|SPECIAL_31|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51": {
+      "content": "〈|SPECIAL_32|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "〈|SPECIAL_33|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "53": {
+      "content": "〈|SPECIAL_34|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "54": {
+      "content": "〈|SPECIAL_35|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "55": {
+      "content": "〈|SPECIAL_36|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "56": {
+      "content": "〈|SPECIAL_37|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57": {
+      "content": "〈|SPECIAL_38|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "〈|SPECIAL_39|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "59": {
+      "content": "〈|SPECIAL_40|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "〈|SPECIAL_41|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "〈|SPECIAL_42|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62": {
+      "content": "〈|SPECIAL_43|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "〈|SPECIAL_44|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64": {
+      "content": "〈|SPECIAL_45|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "〈|SPECIAL_46|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "〈|SPECIAL_47|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "〈|SPECIAL_48|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "〈|SPECIAL_49|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69": {
+      "content": "〈|SPECIAL_50|〉",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "19": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "23": {
+      "content": "<assistant>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "24": {
+      "content": "</assistant>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "25": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "26": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    }
+  },
+  "bos_token": "〈|EOS|〉",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "〈|CLS|〉",
+  "eos_token": "〈|EOS|〉",
+  "extra_special_tokens": {},
+  "mask_token": "〈|MASK|〉",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "〈|PAD|〉",
+  "sep_token": "〈|SEP|〉",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "〈|UNK|〉",
+  "chat_template": "{% include 'chat_template.jinja' %}"
+}